Agentic AI Workload Analyzer

[Mario_D]

Hello Databricks experts,

In Automating Best Practices with Agentic AI Workload Analyzer, Krishna Satyavarapu and Nikhil Mishra mentioned  "The Agentic AI Workload Analyzer". Is it known when this will be available.

cheers

Mario

[Krishna_S · Accepted solution]

Hi @Mario_D 

Yes, the Agentic AI Workload Analyzer is ready, and we are also testing it out with a few customers. Here is the more detailed description of what its latest capabilities are:

If you are interested in trying it out, please reach out to us. Thank you

• Parses code (PySpark/Scala/SQL/Delta Live Tables) and extracts table access patterns, predicates, and write modes.
• Profiles storage/metadata (Unity Catalog, Delta logs) for size, partitioning, clustering/Z-ORDER, OPTIMIZE/VACUUM history, small-file density, stats/ANALYZE coverage.
• Inspects compute (SQL Warehouses, Jobs/Clusters, policies) for autoscaling, photon, DBR/runtime, and spot/provisioning hygiene.
• Scores & prioritizes issues by impact × confidence × blast radius, then generates prescriptive recommendations.
• Publishes findings to Unity Catalog (as metadata/comments/tags) and emits PDF/HTML reports for exec/stakeholders.

[Mario_D]

Hi Krishna,

I'm very much interested in trying it out. What do you need from me.

cheers

Mario

[Thompson2345]

Generative AI is transforming how we handle data and automation. The key challenge now is balancing model creativity with control — ensuring reliable outputs while keeping innovation at the core.